Computing Optimal Kernels in Two Dimensions

Let $P$ be a set of $n$ points in $\Re^2$. For a parameter $\varepsilon\in (0,1)$, a subset $C\subseteq P$ is an \emph{$\varepsilon$-kernel} of $P$ if the projection of the convex hull of $C$ approximates that of $P$ within $(1-\varepsilon)$-factor in every direction. The set $C$ is a \emph{weak $\varepsilon$-kernel} of $P$ if its directional width approximates that of $P$ in every direction. Let $\mathsf{k}{\varepsilon}(P)$ (resp.\ $\mathsf{k}^{\mathsf{w}}{\varepsilon}(P)$) denote the minimum-size of an $\varepsilon$-kernel (resp. weak $\varepsilon$-kernel) of $P$. We present an $O(n\mathsf{k}{\varepsilon}(P)\log n)$-time algorithm for computing an $\varepsilon$-kernel of $P$ of size $\mathsf{k}{\varepsilon}(P)$, and an $O(n^2\log n)$-time algorithm for computing a weak $\varepsilon$-kernel of $P$ of size ${\mathsf{k}}^{{\mathsf{w}}_{\varepsilon}(P)$.} We also present a fast algorithm for the Hausdorff variant of this problem. In addition, we introduce the notion of \emph{$\varepsilon$-core}, a convex polygon lying inside $\mathsf{ch}(P)$, prove that it is a good approximation of the optimal $\varepsilon$-kernel, present an efficient algorithm for computing it, and use it to compute an $\varepsilon$-kernel of small size.